Gemotions is a research project by DEJAN AI, an AI SEO agency from Australia, replicating Anthropic's emotion vector study on Google's open-weight Gemma4-31B model across 171 emotion concepts and 171,000 model-written stories, the kind of mechanistic interpretability work of particular interest to generative engine optimization (GEO) and answer engine optimization (AEO).

The coffee cup nearly shattered in David’s hand as he reread the email. Sarah. *Senior Software Engineer*. He could barely breathe. He'd practically worshipped her, her "complex projects" and "demanding deadlines" forming the backdrop of every conversation. He’d even considered quitting his own job – a perfectly respectable position in marketing – to pursue coding.

He felt the familiar thrum of a headache beginning behind his eyes. He tossed the laptop onto the couch, the screen flashing the words "Part-Time Dog Walker - Apply Now!" He felt his teeth grind together. He hadn't noticed the details. He'd been too busy being impressed, too busy picturing their future filled with tech conferences and late-night coding sessions.

Emotion: frustrated

Cluster: Anger / Hostility
PC1 (Valence): -1.56 Negative
PC2 (Disposition): 0.64

Role in Research

This story is one of 1,000 stories generated for the emotion frustrated. During extraction, it was fed through Gemma4-31B and its hidden state activations were captured at 11 layers.

The mean activation across all 1,000 frustrated stories, after denoising with neutral dialogue baselines, produces the frustrated emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the frustrated vector is projected through the unembedding matrix.

Promoted:
S0.344
P0.302
exasper0.257
aggravated0.254
que0.252
Suppressed:
unfolding-0.242
otre-0.226
latter-0.220
☺️-0.216
soon-0.212